Tag
This paper proposes a neuro-symbolic approach that integrates a MaxSAT oracle as a consistency validator to guide Vision-Language Models (VLMs) in solving Sudoku puzzles, improving logical consistency and the number of solved instances.
LC-ERD is a framework that mines latent logic from LLM-generated reasoning chains to decompose global rewards into step-level signals, enabling self-evolving reasoning without human annotation. It addresses label noise, coarse supervision, and distributional collapse via variational logic potential and multi-agent value decomposition.
This paper introduces RE-Edit, a benchmark for evaluating image editing systems across five reasoning dimensions (physical, environmental, cultural, causal, referential) to assess logical consistency beyond visual plausibility. The benchmark includes 1,000 samples and evaluates ten open-source and two commercial models, showing that even advanced systems struggle with implicit multi-dimensional reasoning.